Digital Twins

ˈdɪʤɪtl twɪnz

A ‘digital twin’ is a digital representation of a physical asset which can be used to monitor, visualise, predict and make decisions about it. (Open Data Institute)

Digital twin technologies are driven by sensors that collect data in real time, enabling a digital representation of a physical process or product. Digital twins can help businesses or decision-makers maintain, optimize, or monitor physical assets, providing specific insights on its health and performance. A traffic model, for example, can be used to monitor and manage real-time pedestrian and road traffic in a city. Energy companies such as General Electric and Chevron use digital twins to monitor wind turbines. Digital twins can also help decision-makers at the state and local level better plan infrastructure or monitor city assets. In Sustainable Cities: Big Data, Artificial Intelligence and the Rise of Green, “Cy-phy” Cities, Claudio Scardovi describes how cities can create digital twins, leveraging data and AI, to test strategies for increasing sustainability, inclusivity, and resilience: 

“Global cities are facing an almost unprecedented challenge of change. As they re-emerge from the Covid 19 pandemic and get ready to face climate change and other, potentially existential threats, they need to look for new ways to support wealth and wellbeing creation […] New digital technologies could be used to design digital and physical twins of cities that are able to feed into each other to optimize their working and ability to create new wealth and wellbeing.” 

The UK National Infrastructure Commission created a framework to support the development of digital twins. Similarly, many European countries encourage urban digital twin initiatives:

“Urban digital twins are a virtual representation of a city’s physical assets, using data, data analytics and machine learning to help stimulate models that can be updated and changed (real-time) as their physical equivalents change. [..]  In terms of rationale, they can bring cost efficiencies, operational efficiencies, better crisis management, more openness and better informed decision-making, more participatory governance or better urban planning.”

Sometimes, however, digital twins fail to accurately reflect real-world developments, leading users to make poor decisions. Fei Tao and Qinglin Qi in Make more digital twins describe data challenges in digital twin technologies, such as inconsistencies with data types and scattered ownership:

“Missing or erroneous data can distort results and obscure faults. The wobbling of a wind turbine, say, would be missed if vibration sensors fail. Beijing-based power company BKC Technology struggled to work out that an oil leak was causing a steam turbine to overheat. It turned out that lubricant levels were missing from its digital twin.”

The uptake of digital twins requires both public and private sector collaboration, and improved data infrastructures. As the Open Data Institute describes, Digital Twins depend on a culture of openness: “open data, open culture, open standards and collaborative models that build trust, reduce cost and create more value.”